scholarly journals Colour and Texture Descriptors for Visual Recognition: A Historical Overview

2021 ◽  
Vol 7 (11) ◽  
pp. 245
Author(s):  
Francesco Bianconi ◽  
Antonio Fernández ◽  
Fabrizio Smeraldi ◽  
Giulia Pascoletti
Keyword(s):  
Deep Learning ◽  
Intelligent Systems ◽  
Visual Recognition ◽  
Early Years ◽  
Data Driven ◽  
Traditional Methods ◽  
Research Attention ◽  
Convolutional Networks ◽  
Advantages And Disadvantages ◽  
Data Driven Approach

Colour and texture are two perceptual stimuli that determine, to a great extent, the appearance of objects, materials and scenes. The ability to process texture and colour is a fundamental skill in humans as well as in animals; therefore, reproducing such capacity in artificial (`intelligent’) systems has attracted considerable research attention since the early 70s. Whereas the main approach to the problem was essentially theory-driven (`hand-crafted’) up to not long ago, in recent years the focus has moved towards data-driven solutions (deep learning). In this overview we retrace the key ideas and methods that have accompanied the evolution of colour and texture analysis over the last five decades, from the `early years’ to convolutional networks. Specifically, we review geometric, differential, statistical and rank-based approaches. Advantages and disadvantages of traditional methods vs. deep learning are also critically discussed, including a perspective on which traditional methods have already been subsumed by deep learning or would be feasible to integrate in a data-driven approach.

Prediction and Interpretable Visualization of Synthetic Reactions Using Graph Convolutional Networks

2019 ◽  
Author(s):  
Shoichi Ishida ◽  
Kei Terayama ◽  
ryosuke kojima ◽  
Kiyosei Takasu ◽  
Yasushi Okuno
Keyword(s):  
Black Box ◽  
Data Driven ◽  
Research Groups ◽  
Reaction Prediction ◽  
Convolutional Networks ◽  
Learning Techniques ◽  
Synthetic Reactions ◽  
Retrosynthetic Analysis ◽  
Data Driven Approach ◽  
Extended Connectivity

<div>Recently, many research groups have been addressing data-driven approaches for reaction prediction and retrosynthetic analysis. Although the performances of the data-driven approach have progressed due to recent advances of machine learning and deep learning techniques, problems such as improving capability of reaction prediction and the black-box problem of neural networks still persist for practical use by chemists. To expand data-driven approaches to chemists, we focused on two challenges: improvement of reaction prediction and interpretability of the prediction. In this paper, we propose an interpretable prediction framework using Graph Convolutional Networks (GCN) for reaction prediction and Integrated Gradients (IGs) for visualization of contributions to the prediction to address these challenges. As a result, our model showed better performances than the approach using Extended-Connectivity Fingerprint (ECFP). Furthermore, IGs based visualization of the GCN prediction successfully highlighted reaction-related atoms.</div>

scholarly journals Risk Prediction for Ship Encounter Situation Awareness Using Long Short-Term Memory Based Deep Learning on Intership Behaviors

2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Jie Ma ◽  
Wenkai Li ◽  
Chengfeng Jia ◽  
Chunwei Zhang ◽  
Yu Zhang
Keyword(s):  
Deep Learning ◽  
Risk Prediction ◽  
Short Term Memory ◽  
Data Driven ◽  
Yangtze River Estuary ◽  
Collision Risk ◽  
Short Term ◽  
Term Memory ◽  
Data Driven Approach ◽  
Long Short Term Memory

Encounter risk prediction is critical for safe ship navigation, especially in congested waters, where ships sail very near to each other during various encounter situations. Prior studies on the risk of ship collisions were unable to address the uncertainty of the encounter process when ignoring the complex motions constituting the dynamic ship encounter behavior, which may seriously affect the risk prediction performance. To fill this gap, a novel AIS data-driven approach is proposed for ship encounter risk prediction by modeling intership behavior patterns. In particular, multidimensional features of intership behaviors are extracted from the AIS trace data to capture spatial dependencies between encountering ships. Then, the challenging task of risk prediction is to discover the complex and uncertain relationship between intership behaviors and future collision risk. To address this issue, we propose a deep learning framework. To represent the temporal dynamics of the encounter process, we use the sliding window technique to generate the sequences of behavioral features. The collision risk level at a future time is taken as the class label of the sequence. Then, the long short-term memory network, which has a strong ability to model temporal dependency and complex patterns, is extended to establish the relationship. The benefit of our approach is that it transforms the complex problem for risk prediction into a time series classification task, which makes collision risk prediction reliable and easier to implement. Experiments were conducted on a set of naturalistic data from various encounter scenarios in the South Channel of the Yangtze River Estuary. The results show that the proposed data-driven approach can predict future collision risk with high accuracy and efficiency. The approach is expected to be applied for the early prediction of encountering ships and as decision support to improve navigation safety.

scholarly journals Contributions towards Data driven Deep Learning methods to predict Steady State Fluid Flow in mechanical Heart Valves

2021 ◽  
Vol 7 (2) ◽  
pp. 625-628
Author(s):  
Jan Oldenburg ◽  
Julian Renkewitz ◽  
Michael Stiehm ◽  
Klaus-Peter Schmitz
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Steady State ◽  
Flow Field ◽  
Heart Valves ◽  
Data Driven ◽  
High Shear ◽  
Blood Flows ◽  
The Neural Network ◽  
Data Driven Approach

Abstract It is commonly accepted that hemodynamic situation is related with cardiovascular diseases as well as clinical post-procedural outcome. In particular, aortic valve stenosis and insufficiency are associated with high shear flow and increased pressure loss. Furthermore, regurgitation, high shear stress and regions of stagnant blood flow are presumed to have an impact on clinical result. Therefore, flow field assessment to characterize the hemodynamic situation is necessary for device evaluation and further design optimization. In-vitro as well as in-silico fluid mechanics methods can be used to investigate the flow through prostheses. In-silico solutions are based on mathematical equitation’s which need to be solved numerically (Computational Fluid Dynamics - CFD). Fundamentally, the flow is physically described by Navier-Stokes. CFD often requires high computational cost resulting in long computation time. Techniques based on deep-learning are under research to overcome this problem. In this study, we applied a deep-learning strategy to estimate fluid flows during peak systolic steady-state blood flows through mechanical aortic valves with varying opening angles in randomly generated aortic root geometries. We used a data driven approach by running 3,500 two dimensional simulations (CFD). The simulation data serves as training data in a supervised deep learning framework based on convolutional neural networks analogous to the U-net architecture. We were able to successfully train the neural network using the supervised data driven approach. The results showing that it is feasible to use a neural network to estimate physiological flow fields in the vicinity of prosthetic heart valves (Validation error below 0.06), by only giving geometry data (Image) into the Network. The neural network generates flow field prediction in real time, which is more than 2500 times faster compared to CFD simulation. Accordingly, there is tremendous potential in the use of AIbased approaches predicting blood flows through heart valves on the basis of geometry data, especially in applications where fast fluid mechanic predictions are desired.

scholarly journals Finding epic moments in live content through deep learning on collective decisions

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Hyeonho Song ◽  
Kunwoo Park ◽  
Meeyoung Cha
Keyword(s):  
Deep Learning ◽  
User Study ◽  
Data Driven ◽  
Live Streaming ◽  
Video Content ◽  
Live Video ◽  
Collective Decisions ◽  
Data Driven Approach ◽  
Streaming Services ◽  
Deep Learning Model

AbstractLive streaming services enable the audience to interact with one another and the streamer over live content. The surging popularity of live streaming platforms has created a competitive environment. To retain existing viewers and attract newcomers, streamers and fans often create a well-condensed summary of the streamed content. However, this process is manual and costly due to the length of online live streaming events. The current study identifies enjoyable moments in user-generated live video content by examining the audiences’ collective evaluation of its epicness. We characterize what features “epic” moments and present a deep learning model to extract them based on analyzing two million user-recommended clips and the associated chat conversations. The evaluation shows that our data-driven approach can identify epic moments from user-generated streamed content that cover various contexts (e.g., victory, funny, awkward, embarrassing). Our user study further demonstrates that the proposed automatic model performs comparably to expert suggestions. We discuss implications of the collective decision-driven extraction in identifying diverse epic moments in a scalable way.

Social Planning

2013 ◽  
Author(s):  
Jon Simon Sager
Keyword(s):  
Problem Solving ◽  
Community Organizations ◽  
Federal Agencies ◽  
Data Driven ◽  
Social Planning ◽  
Future Trends ◽  
Objective Data ◽  
Advantages And Disadvantages ◽  
Target Populations ◽  
Data Driven Approach

Social planning emphasizes the application of rational problem-solving techniques and data-driven approaches to identify, determine, and help coordinate services for target populations. Social planning is carried out by a myriad of organizations—from federal agencies to community organizations—attempting to solve problems ranging from child welfare to aging. The advantages and disadvantages of this empirically objective data-driven approach, including different forms, will be discussed along with past, current, and future trends within the field of social work.

scholarly journals Stochastic Detection of Interior Design Styles Using a Deep-Learning Model for Reference Images

2020 ◽  
Vol 10 (20) ◽  
pp. 7299 ◽  
Author(s):  
Jinsung Kim ◽  
Jin-Kook Lee
Keyword(s):  
Deep Learning ◽  
Interior Design ◽  
Learning Model ◽  
Data Driven ◽  
Data Preparation ◽  
Reference Images ◽  
Data Driven Approach ◽  
Image Set ◽  
Design Style ◽  
Deep Learning Model

This paper describes an approach for identifying and appending interior design style information stochastically with reference images and a deep-learning model. In the field of interior design, design style is a useful concept and has played an important role in helping people understand and communicate interior design. Previous studies have focused on how the interior design style categories can be defined. On the other hand, this paper focuses on how stochastically recognizing the design style of given interior design reference images using a deep learning-based data-driven approach. The proposed method can be summarized as follows: (1) data preparation based on a general design style definition, (2) implementing an interior design style recognition model using a pre-trained VGG16 model, (3) training and evaluating the trained model, and (4) demonstration of stochastic detection of interior design styles for reference images. The result shows that the trained model automatically recognizes the design styles of given interior images with probability values. The recognition results, model, and trained image set contribute to facilitating the management and utilization of an interior design references database.

Sign in / Sign up

Export Citation Format

Share Document